© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2644
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Groovy"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Gro" and its variations, suggesting a focus on identifying references to a specific brand or entity named "Gro."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.81
    BuyableInstoreAndOnline
    -0.77
    TPS
    -0.74
     TAM
    -0.69
    ANI
    -0.69
     IPS
    -0.68
     batter
    -0.67
    Tx
    -0.67
     pm
    -0.65
    ATING
    -0.65
    POSITIVE LOGITS
     Gro
    3.82
    Gro
    2.92
    gro
    1.85
     gro
    1.74
     Kro
    1.24
     Gol
    1.14
     Cro
    1.14
     Grove
    1.13
     Gr
    1.12
     Rocks
    1.12
    Activations Density 0.013%

    No Known Activations